Cardiac or Infectious? Transfer Learning with Chest X-Rays for ER Patient Classification

Stubblefield, Jonathan; Hervert, Mitchell; Causey, Jason; Qualls, Jake; Dong, Wei; Cai, Lingrui; Fowler, Jennifer; Bellis, Emily S.; Walker, Karl; Moore, Jason H.; Nehring, Sara M.; Huang, Xiuzhen

doi:10.1101/2020.04.11.20062091

Cited by 4 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the early scientific literature, digital solutions and innovative technologies were mainly proposed for the diagnosis of COVID-19. In particular, within the reviewed articles, we identified numerous suggestions of the use of AI-powered tools for the diagnosis and screening of SARS-CoV-2 or COVID-19, as reported in Table 4 [20,22,23,25,26,28,30,32,33,38,48,50,54,61,69,70,77,78,94,100,108,109,122,130]. Most studies propose the adoption of AI tools based on the use of computed tomography (CT) data [23,28,33].…”

Section: Diagnosismentioning

confidence: 99%

Adoption of Digital Technologies in Health Care During the COVID-19 Pandemic: Systematic Review of Early Scientific Literature

Golinelli¹,

Boetto²,

Carullo³

et al. 2020

J Med Internet Res

388

256

View full text Add to dashboard Cite

Background The COVID-19 pandemic is favoring digital transitions in many industries and in society as a whole. Health care organizations have responded to the first phase of the pandemic by rapidly adopting digital solutions and advanced technology tools. Objective The aim of this review is to describe the digital solutions that have been reported in the early scientific literature to mitigate the impact of COVID-19 on individuals and health systems. Methods We conducted a systematic review of early COVID-19–related literature (from January 1 to April 30, 2020) by searching MEDLINE and medRxiv with appropriate terms to find relevant literature on the use of digital technologies in response to the pandemic. We extracted study characteristics such as the paper title, journal, and publication date, and we categorized the retrieved papers by the type of technology and patient needs addressed. We built a scoring rubric by cross-classifying the patient needs with the type of technology. We also extracted information and classified each technology reported by the selected articles according to health care system target, grade of innovation, and scalability to other geographical areas. Results The search identified 269 articles, of which 124 full-text articles were assessed and included in the review after screening. Most of the selected articles addressed the use of digital technologies for diagnosis, surveillance, and prevention. We report that most of these digital solutions and innovative technologies have been proposed for the diagnosis of COVID-19. In particular, within the reviewed articles, we identified numerous suggestions on the use of artificial intelligence (AI)–powered tools for the diagnosis and screening of COVID-19. Digital technologies are also useful for prevention and surveillance measures, such as contact-tracing apps and monitoring of internet searches and social media usage. Fewer scientific contributions address the use of digital technologies for lifestyle empowerment or patient engagement. Conclusions In the field of diagnosis, digital solutions that integrate with traditional methods, such as AI-based diagnostic algorithms based both on imaging and clinical data, appear to be promising. For surveillance, digital apps have already proven their effectiveness; however, problems related to privacy and usability remain. For other patient needs, several solutions have been proposed, such as telemedicine or telehealth tools. These tools have long been available, but this historical moment may actually be favoring their definitive large-scale adoption. It is worth taking advantage of the impetus provided by the crisis; it is also important to keep track of the digital solutions currently being proposed to implement best practices and models of care in future and to adopt at least some of the solutions proposed in the scientific literature, especially in national health systems, which have proved to be particularly resistant to the digital transition in recent years.

show abstract

Section: Diagnosismentioning

confidence: 99%

Adoption of Digital Technologies in Health Care During the COVID-19 Pandemic: Systematic Review of Early Scientific Literature

Golinelli¹,

Boetto²,

Carullo³

et al. 2020

J Med Internet Res

388

256

View full text Add to dashboard Cite

show abstract

“…We will use a pretrained CheXNet model to extract imaging features from chest xrays for use in a downstream. This approach was used by this research group previously for predicting the etiology of acute shortness of breath in an ER setting [15]. Summary of this work.…”

Section: Introductionmentioning

confidence: 99%

COVID19 Diagnosis Using Chest X-rays and Transfer Learning

Huang

Stubblefield

2022

Preprint

Self Cite

View full text Add to dashboard Cite

A pandemic of respiratory illnesses from a novel coronavirus known as Sars-CoV-2 has swept across the globe since December of 2019. This is calling upon the research community including medical imaging to provide effective tools for use in combating this virus. Research in biomedical imaging of viral patients is already very active with machine learning models being created for diagnosing Sars-CoV-2 infections in patients using CT scans and chest x-rays. We aim to build upon this research. Here we used a transfer-learning approach to develop models capable of diagnosing COVID19 from chest x-ray. For this work we compiled a dataset of 112120 negative images from the Chest X-Ray 14 and 2725 positive images from public repositories. We tested multiple models, including logistic regression and random forest and XGBoost with and without principal components analysis, using five-fold cross-validation to evaluate recall, precision, and f1-score. These models were compared to a pre-trained deep-learning model for evaluating chest x-rays called COVID-Net. Our best model was XGBoost with principal components with a recall, precision, and f1-score of 0.692, 0.960, 0.804 respectively. This model greatly outperformed COVID-Net which scored 0.987, 0.025, 0.048. This model, with its high precision and reasonable sensitivity, would be most useful as rule-in test for COVID19. Though it outperforms some chemical assays in sensitivity, this model should be studied in patients who would not ordinarily receive a chest x-ray before being used for screening.

show abstract

Study the combination of brain MRI imaging and other datatypes to improve Alzheimer’s disease diagnosis

Stubblefield

Kronberger

Causey

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Alzheimer′s Disease (AD) is a degenerative brain disease and is the most common cause of dementia. Despite being a common disease, AD is poorly understood. Current medical treatments for AD are aimed at slowing the progression of the disease. So early detection of AD is important to intervene at an early stage of the disease. In recent years, by using machine learning predictive algorithms, assisted clinic diagnosis has received great attention due to its success of machine learning advances in the domains of computer vision. In this study, we have combined brain MRI imaging features and the features of other datatypes, and adopted various models, including XGBoost, logistic regression, and k-Nearest Neighbors, to improve AD diagnosis. We evaluated the models on the benchmark dataset of Alzheimer′s Disease Neuroimaging Initiative. Experiment results show that the logistic regression model is the top performer in terms of evaluation metrics of precision, recall, and F1-score. The prediction of the models could provide valuable information for diagnosis and prognosis of patients with suspected Alzheimer′s disease. The XGBoost model achieves a comparable performance and has the potential to serve as a valuable diagnostic tool for patients with suspected AD with its self-validation by re-discovering previously known associations with AD.

show abstract

Cardiac or Infectious? Transfer Learning with Chest X-Rays for ER Patient Classification

Cited by 4 publications

References 20 publications

Adoption of Digital Technologies in Health Care During the COVID-19 Pandemic: Systematic Review of Early Scientific Literature

Adoption of Digital Technologies in Health Care During the COVID-19 Pandemic: Systematic Review of Early Scientific Literature

COVID19 Diagnosis Using Chest X-rays and Transfer Learning

Study the combination of brain MRI imaging and other datatypes to improve Alzheimer’s disease diagnosis

Contact Info

Product

Resources

About